{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T23:10:40Z","timestamp":1743030640668,"version":"3.40.3"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030661243"},{"type":"electronic","value":"9783030661250"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-66125-0_3","type":"book-chapter","created":{"date-parts":[[2020,12,22]],"date-time":"2020-12-22T05:15:17Z","timestamp":1608614117000},"page":"27-45","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dimensionality Reduction and Attention Mechanisms for Extracting Affective State from Sound Spectrograms"],"prefix":"10.1007","author":[{"given":"George","family":"Pikramenos","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Konstantinos","family":"Kechagias","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Theodoros","family":"Psallidas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georgios","family":"Smyrnis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Evaggelos","family":"Spyrou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stavros","family":"Perantonis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,12,23]]},"reference":[{"issue":"1","key":"3_CR1","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1109\/79.911197","volume":"18","author":"R Cowie","year":"2001","unstructured":"Cowie, R., et al.: Emotion recognition in human-computer interaction. IEEE Sign. Process. Mag. 18(1), 32\u201380 (2001)","journal-title":"IEEE Sign. Process. Mag."},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Poria, S., Chaturvedi, I., Cambria, E., Hussain, A.: Convolutional MKL based multimodal emotion recognition and sentiment analysis. In: 2016 IEEE 16th International Conference on Data Mining (ICDM), pp. 439\u2013448. IEEE (2016)","DOI":"10.1109\/ICDM.2016.0055"},{"key":"3_CR3","unstructured":"Zeng, E., Mare, S., Roesner, F.: End user security and privacy concerns with smart homes. In Thirteenth Symposium on Usable Privacy and Security (SOUPS 2017), pp. 65\u201380 (2017)"},{"issue":"11","key":"3_CR4","doi-asserted-by":"publisher","first-page":"2251","DOI":"10.1080\/17470211003721642","volume":"63","author":"DA Sauter","year":"2010","unstructured":"Sauter, D.A., Eisner, F., Calder, A.J., Scott, S.K.: Perceptual cues in nonverbal vocal expressions of emotion. Quart. J. Exp. Psychol. 63(11), 2251\u20132272 (2010)","journal-title":"Quart. J. Exp. Psychol."},{"issue":"2","key":"3_CR5","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s10462-012-9368-5","volume":"43","author":"CN Anagnostopoulos","year":"2015","unstructured":"Anagnostopoulos, C.N., Iliou, T., Giannoukos, I.: Features and classifiers for emotion recognition from speech: a survey from 2000 to 2011. Artif. Intell. Rev. 43(2), 155\u2013177 (2015). https:\/\/doi.org\/10.1007\/s10462-012-9368-5","journal-title":"Artif. Intell. Rev."},{"issue":"3","key":"3_CR6","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1016\/j.patcog.2010.09.020","volume":"44","author":"M El Ayadi","year":"2011","unstructured":"El Ayadi, M., Kamel, M.S., Karray, F.: Survey on speech emotion recognition: features, classification schemes, and databases. Pattern Recogn. 44(3), 572\u2013587 (2011)","journal-title":"Pattern Recogn."},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Giannakopoulos, T., Pikrakis, A.: Introduction to Audio Analysis: A MATLAB\u00ae Approach. Academic Press, Cambridge (2014)","DOI":"10.1016\/B978-0-08-099388-1.00001-7"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Drakopoulos, G., Pikramenos, G., Spyrou, E.D., Perantonis, S.J.: Emotion recognition from speech: a survey. In: WEBIST, pp. 432\u2013439 (2019)","DOI":"10.5220\/0008495000002366"},{"key":"3_CR9","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Badshah, A.M., Ahmad, J., Rahim, N., Baik, S.W.: Speech emotion recognition from spectrograms with deep convolutional neural network. In: 2017 International Conference on Platform Technology and Service (PlatCon), pp. 1\u20135. IEEE (2017)","DOI":"10.1109\/PlatCon.2017.7883728"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Satt, A., Rozenberg, S., Hoory, R.: Efficient emotion recognition from speech using deep learning on spectrograms (2017)","DOI":"10.21437\/Interspeech.2017-200"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"He, L., Lech, M., Maddage, N., Allen, N.: Stress and emotion recognition using log-Gabor filter analysis of speech spectrograms. In 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, pp. 1\u20136. IEEE (2009)","DOI":"10.1109\/ACII.2009.5349454"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Pikramenos, G., Smyrnis, G., Vernikos, I., Konidaris, T., Spyrou, E., Perantonis, S.J.: Sentiment analysis from sound spectrograms via soft BoVW and temporal structure modelling. In: ICPRAM, pp. 361\u2013369 (2020)","DOI":"10.5220\/0009174503610369"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Lim, W., Jang, D., Lee, T.: Speech emotion recognition using convolutional and recurrent neural networks. In: 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), pp. 1\u20134. IEEE (2016)","DOI":"10.1109\/APSIPA.2016.7820699"},{"issue":"5","key":"3_CR15","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1109\/TMM.2008.927665","volume":"10","author":"Y Wang","year":"2008","unstructured":"Wang, Y., Guan, L.: Recognizing human emotional state from audiovisual signals. IEEE Trans. Multimedia 10(5), 936\u2013946 (2008)","journal-title":"IEEE Trans. Multimedia"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Nogueiras, A., Moreno, A., Bonafonte, A., & Mari\u00f1o, J. B.: Speech emotion recognition using hidden Markov models. In Seventh European Conference on Speech Communication and Technology (2001)","DOI":"10.21437\/Eurospeech.2001-627"},{"issue":"1","key":"3_CR17","doi-asserted-by":"publisher","first-page":"20","DOI":"10.3390\/technologies7010020","volume":"7","author":"E Spyrou","year":"2019","unstructured":"Spyrou, E., Nikopoulou, R., Vernikos, I., Mylonas, P.: Emotion recognition from speech using the bag-of-visual words on audio segment spectrograms. Technologies 7(1), 20 (2019)","journal-title":"Technologies"},{"issue":"2","key":"3_CR18","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1109\/MSP.2006.1621452","volume":"23","author":"A Hanjalic","year":"2006","unstructured":"Hanjalic, A.: Extracting moods from pictures and sounds: Towards truly personalized TV. IEEE Sign. Process. Mag. 23(2), 90\u2013100 (2006)","journal-title":"IEEE Sign. Process. Mag."},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Rozgi\u0107, V., Ananthakrishnan, S., Saleem, S., Kumar, R., Vembu, A.N., Prasad, R.: Emotion recognition using acoustic and lexical features. In Thirteenth Annual Conference of the International Speech Communication Association (2012)","DOI":"10.21437\/Interspeech.2012-118"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: ORB: an efficient alternative to SIFT or SURF. In: 2011 International Conference on Computer Vision, pp. 2564\u20132571. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"3_CR21","series-title":"Advances in Intelligent Systems and Computing","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1007\/978-3-030-29513-4_31","volume-title":"Intelligent Systems and Applications","author":"D Hu","year":"2020","unstructured":"Hu, D.: An introductory survey on attention mechanisms in NLP problems. In: Bi, Y., Bhatia, R., Kapoor, S. (eds.) IntelliSys 2019. AISC, vol. 1038, pp. 432\u2013448. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-29513-4_31"},{"issue":"8","key":"3_CR22","doi-asserted-by":"publisher","first-page":"1836","DOI":"10.1093\/cercor\/bhs164","volume":"23","author":"LB Kristensen","year":"2013","unstructured":"Kristensen, L.B., Wang, L., Petersson, K.M., Hagoort, P.: The interface between language and attention: prosodic focus marking recruits a general attention network in spoken language comprehension. Cereb. Cortex 23(8), 1836\u20131848 (2013)","journal-title":"Cereb. Cortex"},{"key":"3_CR23","unstructured":"Galassi, A., Lippi, M., Torroni, P.: Attention, please! a critical review of neural attention models in natural language processing. arXiv preprint. arXiv:1902.02181 (2019)"},{"issue":"8","key":"3_CR24","doi-asserted-by":"publisher","first-page":"2203","DOI":"10.1109\/TMM.2014.2360798","volume":"16","author":"Q Mao","year":"2014","unstructured":"Mao, Q., Dong, M., Huang, Z., Zhan, Y.: Learning salient features for speech emotion recognition using convolutional neural networks. IEEE Trans. Multimedia 16(8), 2203\u20132213 (2014)","journal-title":"IEEE Trans. Multimedia"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Burkhardt, F., Paeschke, A., Rolfes, M., Sendlmeier, W. F., Weiss, B.: A database of German emotional speech. In Ninth European Conference on Speech Communication and Technology (2005)","DOI":"10.21437\/Interspeech.2005-446"},{"key":"3_CR26","unstructured":"Costantini, G., Iaderola, I., Paoloni, A., Todisco, M.: EMOVO corpus: an Italian emotional speech database. In: International Conference on Language Resources and Evaluation (LREC 2014), pp. 3501\u20133504. European Language Resources Association (ELRA) (2014)"},{"key":"3_CR27","unstructured":"Jackson, P., Haq, S.: Surrey audio-visual expressed emotion (SAVEE) database. University of Surrey, Guildford, UK (2014)"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., Tang, X.: Residual attention network for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2017)","DOI":"10.1109\/CVPR.2017.683"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Salazar, J., Kirchhoff, K., Huang, Z.: Self-attention networks for connectionist temporal classification in speech recognition. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7115\u20137119. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8682539"},{"key":"3_CR30","unstructured":"Lin, Z., Feng, M., Santos, C.N.D., Yu, M., Xiang, B., Zhou, B., Bengio, Y.: A structured self-attentive sentence embedding. arXiv preprint. arXiv:1703.03130 (2017)"},{"key":"3_CR31","doi-asserted-by":"publisher","first-page":"98005","DOI":"10.1109\/ACCESS.2019.2929512","volume":"7","author":"Z Yan","year":"2019","unstructured":"Yan, Z., Liu, W., Wen, S., Yang, Y.: Multi-label image classification by feature attention network. IEEE Access 7, 98005\u201398013 (2019)","journal-title":"IEEE Access"},{"key":"3_CR32","unstructured":"Mehrabian, A.: Framework for a comprehensive description and measurement of emotional states. Genet. Soc. Gen. Psychol. Monogr. 121, 339\u2013361 (1995)"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Sculley, D.: Web-scale k-means clustering. In: Proceedings of the 19th International Conference on World Wide Web, pp. 1177\u20131178 (2010)","DOI":"10.1145\/1772690.1772862"},{"key":"3_CR34","doi-asserted-by":"crossref","unstructured":"Binali, H., Wu, C., Potdar, V.: Computational approaches for emotion detection in text. In: 4th IEEE International Conference on Digital Ecosystems and Technologies, pp. 172\u2013177. IEEE (2010)","DOI":"10.1109\/DEST.2010.5610650"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Jin, Q., Li, C., Chen, S., Wu, H.: Speech emotion recognition with acoustic and lexical features. In 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4749\u20134753. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178872"},{"issue":"1","key":"3_CR36","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1109\/TSA.2005.860344","volume":"14","author":"L Lu","year":"2005","unstructured":"Lu, L., Liu, D., Zhang, H.J.: Automatic mood detection and tracking of music audio signals. IEEE Trans. Audio Speech Lang. Process. 14(1), 5\u201318 (2005)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"2","key":"3_CR37","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1109\/TASL.2007.911513","volume":"16","author":"YH Yang","year":"2008","unstructured":"Yang, Y.H., Lin, Y.C., Su, Y.F., Chen, H.H.: A regression approach to music emotion recognition. IEEE Trans. Audio Speech Lang. Process. 16(2), 448\u2013457 (2008)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"3_CR38","doi-asserted-by":"crossref","unstructured":"Panda, R., Malheiro, R.M., Paiva, R.P.: Novel audio features for music emotion recognition. IEEE Trans. Affect. Comput. 11, 614\u2013626 (2018)","DOI":"10.1109\/TAFFC.2018.2820691"},{"issue":"10\u201311","key":"3_CR39","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1016\/j.specom.2007.01.010","volume":"49","author":"M Grimm","year":"2007","unstructured":"Grimm, M., Kroschel, K., Mower, E., Narayanan, S.: Primitives-based evaluation and estimation of emotions in speech. Speech Commun. 49(10\u201311), 787\u2013800 (2007)","journal-title":"Speech Commun."},{"issue":"2","key":"3_CR40","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91\u2013110 (2004). https:\/\/doi.org\/10.1023\/B:VISI.0000029664.99615.94","journal-title":"Int. J. Comput. Vis."},{"key":"3_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1007\/11744023_32","volume-title":"Computer Vision \u2013 ECCV 2006","author":"H Bay","year":"2006","unstructured":"Bay, H., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 404\u2013417. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11744023_32"},{"key":"3_CR42","doi-asserted-by":"crossref","unstructured":"W\u00f6llmer, M., et al.: Abandoning emotion classes-towards continuous emotion recognition with modelling of long-range dependencies. In: Proceedings of the 9th Interspeech 2008 Incorp. 12th Australasian International Conference on Speech Science and Technology SST 2008, Brisbane, Australia, pp. 597\u2013600 (2008)","DOI":"10.21437\/Interspeech.2008-192"},{"key":"3_CR43","doi-asserted-by":"crossref","unstructured":"Giannakopoulos, T., Pikrakis, A., Theodoridis, S.: A dimensional approach to emotion recognition of speech from movies. In: 2009 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 65\u201368. IEEE (2009)","DOI":"10.1109\/ICASSP.2009.4959521"},{"key":"3_CR44","unstructured":"Lee, H., Pham, P., Largman, Y., Ng, A.Y.: Unsupervised feature learning for audio classification using convolutional deep belief networks. In: Advances in Neural Information Processing Systems, pp. 1096\u20131104 (2009)"},{"issue":"4","key":"3_CR45","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1109\/89.917689","volume":"9","author":"T Zhang","year":"2001","unstructured":"Zhang, T., Kuo, C.C.J.: Audio content analysis for online audiovisual data segmentation and classification. IEEE Trans. Speech Audio Process. 9(4), 441\u2013457 (2001)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"3_CR46","doi-asserted-by":"crossref","unstructured":"Busso, C., et al.: IEMOCAP: interactive emotional dyadic motion capture database. Lang. Resour. Eval. 42(4), 335 (2008)","DOI":"10.1007\/s10579-008-9076-6"},{"key":"3_CR47","doi-asserted-by":"crossref","unstructured":"Plutchik, R.: A general psychoevolutionary theory of emotion. In: Theories of Emotion, pp. 3\u201333. Academic press, Cambridge (1980)","DOI":"10.1016\/B978-0-12-558701-3.50007-7"},{"key":"3_CR48","doi-asserted-by":"crossref","unstructured":"Papakostas, M., et al.: Deep visual attributes vs. hand-crafted audio features on multidomain speech emotion recognition. Computation 5(2), 26 (2017)","DOI":"10.3390\/computation5020026"},{"key":"3_CR49","doi-asserted-by":"publisher","first-page":"3925","DOI":"10.1016\/j.sbspro.2012.06.173","volume":"46","author":"JG Marti\u00ednez","year":"2012","unstructured":"Marti\u00ednez, J.G.: Recognition and emotions. A critical approach on education. Procedia Soc. Behav. Sci. 46, 3925\u20133930 (2012)","journal-title":"Procedia Soc. Behav. Sci."},{"issue":"1","key":"3_CR50","doi-asserted-by":"publisher","first-page":"012053","DOI":"10.1088\/1742-6596\/450\/1\/012053","volume":"450","author":"A Tickle","year":"2013","unstructured":"Tickle, A., Raghu, S., Elshaw, M.: Emotional recognition from the speech signal for a virtual education agent. J. Phys. Conf. Ser. 450(1), 012053 (2013)","journal-title":"J. Phys. Conf. Ser."},{"issue":"5","key":"3_CR51","doi-asserted-by":"publisher","first-page":"1367","DOI":"10.1007\/s10639-015-9388-2","volume":"21","author":"K Bahreini","year":"2016","unstructured":"Bahreini, K., Nadolski, R., Westera, W.: Towards real-time speech emotion recognition for affective e-learning. Educ. Inf. Technol. 21(5), 1367\u20131386 (2016). https:\/\/doi.org\/10.1007\/s10639-015-9388-2","journal-title":"Educ. Inf. Technol."},{"key":"3_CR52","doi-asserted-by":"crossref","unstructured":"Busso, C., et al.: Analysis of emotion recognition using facial expressions, speech and multimodal information. In: Proceedings of the 6th International Conference on Multimodal Interfaces, pp. 205\u2013211 (2004)","DOI":"10.1145\/1027933.1027968"},{"key":"3_CR53","doi-asserted-by":"crossref","unstructured":"W\u00f6llmer, M., Metallinou, A., Eyben, F., Schuller, B., Narayanan, S.: Context-sensitive multimodal emotion recognition from speech and facial expression using bidirectional LSTM modeling. In: Proceedings of the INTERSPEECH 2010, Makuhari, Japan, pp. 2362\u20132365 (2010)","DOI":"10.21437\/Interspeech.2010-646"},{"key":"3_CR54","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/j.patrec.2014.10.015","volume":"66","author":"E Trentin","year":"2015","unstructured":"Trentin, E., Scherer, S., Schwenker, F.: Emotion recognition from speech signals via a probabilistic echo-state network. Pattern Recogn. Lett. 66, 4\u201312 (2015)","journal-title":"Pattern Recogn. Lett."},{"issue":"8","key":"3_CR55","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"3_CR56","doi-asserted-by":"crossref","unstructured":"Sak, H., Senior, A.W., Beaufays, F.: Long short-term memory recurrent neural network architectures for large scale acoustic modeling (2014)","DOI":"10.21437\/Interspeech.2014-80"},{"key":"3_CR57","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1007\/3-540-44673-7_8","volume-title":"Machine Learning and Its Applications","author":"S Theodoridis","year":"2001","unstructured":"Theodoridis, S., Koutroumbas, K.: Pattern recognition and neural networks. In: Paliouras, G., Karkaletsis, V., Spyropoulos, C.D. (eds.) ACAI 1999. LNCS (LNAI), vol. 2049, pp. 169\u2013195. Springer, Heidelberg (2001). https:\/\/doi.org\/10.1007\/3-540-44673-7_8"},{"key":"3_CR58","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1007\/978-3-030-27202-9_29","volume-title":"Image Analysis and Recognition","author":"M Aminbeidokhti","year":"2019","unstructured":"Aminbeidokhti, M., Pedersoli, M., Cardinal, P., Granger, E.: Emotion recognition with spatial attention and temporal softmax pooling. In: Karray, F., Campilho, A., Yu, A. (eds.) ICIAR 2019. LNCS, vol. 11662, pp. 323\u2013331. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-27202-9_29"},{"key":"3_CR59","doi-asserted-by":"crossref","unstructured":"Gupta, A., Agrawal, D., Chauhan, H., Dolz, J., Pedersoli, M.: An attention model for group-level emotion recognition. In: Proceedings of the 20th ACM International Conference on Multimodal Interaction, pp. 611\u2013615 (2018)","DOI":"10.1145\/3242969.3264985"},{"key":"3_CR60","doi-asserted-by":"crossref","unstructured":"Tarantino, L., Garner, P.N., Lazaridis, A.: Self-Attention for speech emotion recognition. In: INTERSPEECH, pp. 2578\u20132582 (2019)","DOI":"10.21437\/Interspeech.2019-2822"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition Applications and Methods"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-66125-0_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,22]],"date-time":"2024-12-22T00:02:45Z","timestamp":1734825765000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-66125-0_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030661243","9783030661250"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-66125-0_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"23 December 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPRAM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition Applications and Methods","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Valletta","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malta","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 February 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 February 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpram2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.icpram.org\/?y=2020","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Primoris","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"102","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}